Neural Bayesian Filtering

ICLR 2026 Conference Submission19794 Authors

Keywords: Partially observable systems, belief state modeling, particle filtering, bayesian filtering, normalizing flows

TL;DR: Neural Bayesian Filtering embeds beliefs and tracks multimodal posteriors by filtering over embeddings.

Abstract:

We present Neural Bayesian Filtering (NBF), an algorithm for maintaining distributions over hidden states, called beliefs, in partially observable systems. NBF is trained to find a good latent representation of the beliefs induced by a task. It maps beliefs to fixed-length embedding vectors, which condition generative models for sampling. During filtering, particle-style updates compute posteriors in this embedding space using incoming observations and the environment’s dynamics. NBF combines the computational efficiency of classical filters with the expressiveness of deep generative models—tracking rapidly shifting, multimodal beliefs
while mitigating the risk of particle impoverishment. We validate NBF in state estimation tasks in three partially observable environments.

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

Submission Number: 19794